def get_sources(self, video): hosters = [] sources = {} source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=.5) match = re.search("load_player\('([^']+)", html) if not match: return hosters headers = {'Referer': page_url, 'Server': 'cloudflare-nginx', 'Accept': 'text/html, */*; q=0.01', 'Accept-Language': 'en-US,en;q=0.5', 'Accept-Formating': 'application/json, text/javascript', 'Accept-Encoding': 'gzip, deflate'} headers.update(XHR) params = {'id': match.group(1)} player_url = scraper_utils.urljoin(self.base_url, PLAYER_URL) html = self._http_get(player_url, params=params, headers=headers, cache_limit=1) js_data = scraper_utils.parse_json(html, player_url) pl_url = js_data.get('value') or js_data.get('download') if not pl_url: return hosters headers = {'Referer': page_url} if pl_url.startswith('//'): pl_url = 'https:' + pl_url html = self._http_get(pl_url, headers=headers, allow_redirect=False, cache_limit=0) if html.startswith('http'): streams = [(html, '')] else: js_data = scraper_utils.parse_json(html, pl_url) try: streams = [(source['file'], source.get('label', '')) for source in js_data['playlist'][0]['sources']] except: streams = [] for stream in streams: stream_url, label = stream if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo': sources[stream_url] = {'quality': scraper_utils.gv_get_quality(stream_url), 'direct': True} else: if label: quality = scraper_utils.height_get_quality(label) else: quality = QUALITIES.HIGH sources[stream_url] = {'quality': quality, 'direct': False} for source, value in sources.iteritems(): direct = value['direct'] quality = value['quality'] if direct: host = scraper_utils.get_direct_hostname(self, source) else: host = urlparse.urlparse(source).hostname stream_url = source + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua()}) hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': direct} hosters.append(hoster) return hosters
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, require_debrid=True, cache_limit=.5) fragment = dom_parser2.parse_dom(html, 'table', {'class': 'links-table'}) if not fragment: return hosters for _attrs, row in dom_parser2.parse_dom(fragment[0].content, 'tr'): match = re.search( "playVideo\.bind\(.*?'([^']+)(?:[^>]*>){2}(.*?)</td>", row, re.DOTALL) if not match: continue stream_url, release = match.groups() if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo': sources = scraper_utils.parse_google(self, stream_url) else: sources = [stream_url] for source in sources: host = scraper_utils.get_direct_hostname(self, source) if host == 'gvideo': quality = scraper_utils.gv_get_quality(source) direct = True else: host = urlparse.urlparse(source).hostname if video.video_type == VIDEO_TYPES.MOVIE: meta = scraper_utils.parse_movie_link(release) else: meta = scraper_utils.parse_episode_link(release) base_quality = scraper_utils.height_get_quality( meta['height']) quality = scraper_utils.get_quality( video, host, base_quality) direct = False hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': source, 'direct': direct } hosters.append(hoster) return hosters
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters headers = { 'User-Agent': scraper_utils.get_ua(), 'Referer': self.base_url + source_url } if video.video_type == VIDEO_TYPES.MOVIE: meta = scraper_utils.parse_movie_link(source_url) stream_url = source_url + scraper_utils.append_headers(headers) quality = scraper_utils.height_get_quality(meta['height']) hoster = { 'multi-part': False, 'host': scraper_utils.get_direct_hostname(self, stream_url), 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True } if 'format' in meta: hoster['format'] = meta['format'] hosters.append(hoster) else: for episode in self.__match_episode(source_url, video): meta = scraper_utils.parse_episode_link(episode['title']) stream_url = episode['url'] + scraper_utils.append_headers( headers) stream_url = stream_url.replace(self.base_url, '') quality = scraper_utils.height_get_quality(meta['height']) hoster = { 'multi-part': False, 'host': scraper_utils.get_direct_hostname(self, stream_url), 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True } if 'format' in meta: hoster['format'] = meta['format'] if 'size' in episode: hoster['size'] = scraper_utils.format_size( int(episode['size'])) hosters.append(hoster) return hosters
def get_sources(self, video): source_url = self.get_url(video) hosters = [] if not source_url or source_url == FORCE_NO_MATCH: return hosters url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(url, cache_limit=.5) sources = self.__get_posts(html) sources.update(self.__get_ajax(html, url)) sources.update(self.__get_embedded(html, url)) for source in sources: stream_url = source + scraper_utils.append_headers( {'User-Agent': scraper_utils.get_ua()}) host = scraper_utils.get_direct_hostname(self, source) hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': sources[source], 'views': None, 'rating': None, 'url': stream_url, 'direct': True, 'subs': 'Turkish subtitles' } hosters.append(hoster) return hosters
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters query = scraper_utils.parse_query(source_url) if 'id' in query: vid_type = 'movies' if video.video_type == VIDEO_TYPES.MOVIE else 'episodes' url = scraper_utils.urljoin( self.base_url, '/api/v2/%s/%s' % (vid_type, query['id'])) js_data = self._http_get(url, cache_limit=.5) if 'url' in js_data: stream_url = js_data['url'] quality = QUALITIES.HD720 hoster = { 'multi-part': False, 'host': scraper_utils.get_direct_hostname(self, stream_url), 'class': self, 'url': stream_url, 'quality': quality, 'views': None, 'rating': None, 'direct': True } hosters.append(hoster) return hosters
def __get_links_from_json2(self, url, page_url, video_type): sources = {} headers = {'Referer': page_url} headers.update(XHR) html = self._http_get(url, headers=headers, cache_limit=0) js_data = scraper_utils.parse_json(html, url) try: playlist = js_data.get('playlist', []) for source in playlist[0].get('sources', []): stream_url = source['file'] if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo': quality = scraper_utils.gv_get_quality(stream_url) elif 'label' in source: quality = scraper_utils.height_get_quality(source['label']) else: if video_type == VIDEO_TYPES.MOVIE: meta = scraper_utils.parse_movie_link(stream_url) else: meta = scraper_utils.parse_episode_link(stream_url) quality = scraper_utils.height_get_quality(meta['height']) sources[stream_url] = {'quality': quality, 'direct': True} logger.log( 'Adding stream: %s Quality: %s' % (stream_url, quality), log_utils.LOGDEBUG) except Exception as e: logger.log('Exception during yesmovies extract: %s' % (e), log_utils.LOGDEBUG) return sources
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters for stream in self.__get_videos(source_url, video): if video.video_type == VIDEO_TYPES.EPISODE and not scraper_utils.release_check( video, stream['name']): continue host = scraper_utils.get_direct_hostname(self, stream['url']) hoster = { 'multi-part': False, 'class': self, 'views': None, 'url': stream['url'], 'rating': None, 'host': host, 'quality': stream['quality'], 'direct': True } if 'size' in stream: hoster['size'] = scraper_utils.format_size(stream['size']) if 'name' in stream: hoster['extra'] = stream['name'] hosters.append(hoster) return hosters
def __get_episode_sources(self, source_url, video): hosters = [] links = self.__find_episode(source_url, video) if not links: return hosters hash_data = self.__get_hash_data([link[0] for link in links]) for link in links: try: status = hash_data['hashes'][link[0]]['status'] except KeyError: status = '' if status.lower() != 'finished': continue stream_url = 'hash_id=%s' % (link[0]) host = scraper_utils.get_direct_hostname(self, stream_url) quality = scraper_utils.blog_get_quality(video, link[1], '') hoster = { 'multi-part': False, 'class': self, 'views': None, 'url': stream_url, 'rating': None, 'host': host, 'quality': quality, 'direct': True } hoster['extra'] = link[1] hosters.append(hoster) return hosters
def __get_links(self, html): hosters = [] r = re.search('tlas\("([^"]+)', html) if r: plaintext = self.__caesar( self.__get_f(self.__caesar(r.group(1), 13)), 13) sources = scraper_utils.parse_sources_list(self, plaintext) for source in sources: stream_url = source + scraper_utils.append_headers( { 'User-Agent': scraper_utils.get_ua(), 'Cookie': self._get_stream_cookies() }) host = scraper_utils.get_direct_hostname(self, stream_url) hoster = { 'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': sources[source]['quality'], 'rating': None, 'views': None, 'direct': True } hosters.append(hoster) return hosters
def __get_gk_links(self, html): sources = {} match = re.search('{link\s*:\s*"([^"]+)', html) if match: iframe_url = match.group(1) data = {'link': iframe_url} headers = {'Referer': iframe_url} html = self._http_get(self.gk_url, data=data, headers=headers, cache_limit=.5) js_data = scraper_utils.parse_json(html, self.gk_url) links = js_data.get('link', []) if isinstance(links, basestring): links = [{'link': links}] for link in links: stream_url = link['link'] if scraper_utils.get_direct_hostname(self, stream_url) == 'openload.co': quality = scraper_utils.gv_get_quality(stream_url) direct = True elif 'label' in link: quality = scraper_utils.height_get_quality(link['label']) direct = True else: quality = QUALITIES.HIGH direct = False sources[stream_url] = {'quality': quality, 'direct': direct} return sources
def get_sources(self, video): source_url = self.get_url(video) hosters = [] if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=.5) fragment = dom_parser2.parse_dom(html, 'div', {'class': 'film-container'}) if fragment: iframe_url = dom_parser2.parse_dom(fragment[0].content, 'iframe', req='src') if iframe_url: iframe_url = scraper_utils.urljoin(self.base_url, iframe_url[0].attrs['src']) headers = {'Referer': page_url} html = self._http_get(iframe_url, headers=headers, cache_limit=.5) sources = scraper_utils.parse_sources_list(self, html) for source in sources: quality = sources[source]['quality'] host = scraper_utils.get_direct_hostname(self, source) stream_url = source + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua(), 'Referer': iframe_url}) hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True} match = re.search('(\d+[a-z]bps)', source) if match: hoster['extra'] = match.group(1) hosters.append(hoster) hosters.sort(key=lambda x: x.get('extra', ''), reverse=True) return hosters
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=8) for attrs, _content in dom_parser2.parse_dom(html, 'a', req='href'): stream_url = attrs['href'] if MOVIE_URL in stream_url: meta = scraper_utils.parse_movie_link(stream_url) stream_url = scraper_utils.pathify_url( stream_url) + scraper_utils.append_headers( {'User-Agent': scraper_utils.get_ua()}) quality = scraper_utils.height_get_quality(meta['height']) hoster = { 'multi-part': False, 'host': scraper_utils.get_direct_hostname(self, stream_url), 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True } if 'format' in meta: hoster['format'] = meta['format'] hosters.append(hoster) return hosters
def __get_cloud_links(self, html, page_url, sub): hosters = [] html = html.replace('\\"', '"').replace('\\/', '/') match = re.search("dizi_kapak_getir\('([^']+)", html) if match: ep_id = match.group(1) for attrs, _content in dom_parser2.parse_dom(html, 'script', {'data-cfasync': 'false'}, req='src'): script_url = attrs['src'] html = self._http_get(script_url, cache_limit=24) match1 = re.search("var\s+kapak_url\s*=\s*'([^']+)", html) match2 = re.search("var\s+aCtkp\s*=\s*'([^']+)", html) if match1 and match2: link_url = '%s?fileid=%s&access_token=%s' % (match1.group(1), ep_id, match2.group(1)) headers = {'Referer': page_url} html = self._http_get(link_url, headers=headers, cache_limit=.5) js_data = scraper_utils.parse_json(html, link_url) for variant in js_data.get('variants', {}): stream_host = random.choice(variant.get('hosts', [])) if stream_host: stream_url = stream_host + variant['path'] + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua(), 'Referer': page_url}) if not stream_url.startswith('http'): stream_url = 'http://' + stream_url host = scraper_utils.get_direct_hostname(self, stream_url) if 'width' in variant: quality = scraper_utils.width_get_quality(variant['width']) elif 'height' in variant: quality = scraper_utils.height_get_quality(variant['height']) else: quality = QUALITIES.HIGH hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True} hoster['subs'] = sub hosters.append(hoster) return hosters
def __create_source(self, stream_url, height, page_url, subs=False, direct=True): if direct: stream_url = stream_url.replace('\\/', '/') if self.get_name().lower() in stream_url: headers = {'Referer': page_url} redir_url = self._http_get(stream_url, headers=headers, method='HEAD', allow_redirect=False, cache_limit=.25) if redir_url.startswith('http'): stream_url = redir_url stream_url += scraper_utils.append_headers( {'User-Agent': scraper_utils.get_ua()}) else: stream_url += scraper_utils.append_headers({ 'User-Agent': scraper_utils.get_ua(), 'Referer': page_url, 'Cookie': self._get_stream_cookies() }) else: stream_url += scraper_utils.append_headers({ 'User-Agent': scraper_utils.get_ua(), 'Referer': page_url }) host = scraper_utils.get_direct_hostname(self, stream_url) else: host = urlparse.urlparse(stream_url).hostname if host == 'gvideo': quality = scraper_utils.gv_get_quality(stream_url) else: quality = scraper_utils.height_get_quality(height) hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': direct } if subs: hoster['subs'] = 'Turkish Subtitles' return hoster
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(url, cache_limit=.5) views = None fragment = dom_parser2.parse_dom( html, 'img', {'src': re.compile('[^"]*view_icon.png')}) if fragment: match = re.search('(\d+)', fragment[0].content) if match: views = match.group(1) match = re.search('href="([^"]+-full-movie-[^"]+)', html) if match: url = match.group(1) html = self._http_get(url, cache_limit=.5) sources = self.__get_embedded(html) for link in dom_parser2.parse_dom(html, 'span', {'class': 'btn-eps'}, req='link'): link = link.attrs['link'] ajax_url = scraper_utils.urljoin(self.base_url, AJAX_URL) headers = {'Referer': url} headers.update(XHR) html = self._http_get(ajax_url, params={'v': link}, headers=headers, cache_limit=.5) sources.update(self.__get_sources(html)) for source in sources: if sources[source]['direct']: host = scraper_utils.get_direct_hostname(self, source) else: host = urlparse.urlparse(source).hostname stream_url = source + scraper_utils.append_headers( {'User-Agent': scraper_utils.get_ua()}) direct = sources[source]['direct'] quality = sources[source]['quality'] hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': views, 'rating': None, 'url': stream_url, 'direct': direct } hosters.append(hoster) return hosters
def get_sources(self, video): source_url = self.get_url(video) hosters = [] sources = {} headers = {'Accept-Language': 'en-US,en;q=0.5'} if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, headers=headers, cache_limit=2) if video.video_type == VIDEO_TYPES.MOVIE: sources.update(self.__scrape_sources(html, page_url)) pages = set([ r.attrs['href'] for r in dom_parser2.parse_dom( html, 'a', {'class': 'btn-eps'}, req='href') ]) active = set([ r.attrs['href'] for r in dom_parser2.parse_dom( html, 'a', {'class': 'active'}, req='href') ]) for page in list(pages - active): page_url = scraper_utils.urljoin(self.base_url, page) html = self._http_get(page_url, headers=headers, cache_limit=2) sources.update(self.__scrape_sources(html, page_url)) else: for page in self.__match_episode(video, html): page_url = scraper_utils.urljoin(self.base_url, page) html = self._http_get(page_url, headers=headers, cache_limit=2) sources.update(self.__scrape_sources(html, page_url)) for source, values in sources.iteritems(): if not source.lower().startswith('http'): continue if values['direct']: host = scraper_utils.get_direct_hostname(self, source) if host != 'gvideo': stream_url = source + scraper_utils.append_headers( { 'User-Agent': scraper_utils.get_ua(), 'Referer': page_url }) else: stream_url = source else: host = urlparse.urlparse(source).hostname stream_url = source hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': values['quality'], 'views': None, 'rating': None, 'url': stream_url, 'direct': values['direct'] } hosters.append(hoster) return hosters
def __get_js_sources(self, js_data, page_url): hosters = [] for key in js_data: if 'videolink' in key: stream_url = js_data[key] if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo': hosters.append( self.__create_source(stream_url, 480, page_url)) return hosters
def __get_sources(self, html, label): sources = {} for attrs, _label in dom_parser2.parse_dom(html, 'source', req='src'): if scraper_utils.get_direct_hostname(self, attrs['src']) == 'gvideo': quality = scraper_utils.gv_get_quality(attrs['src']) else: quality = Q_MAP.get(label.upper(), QUALITIES.HIGH) sources[attrs['src']] = {'direct': True, 'quality': quality} return sources
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(url, cache_limit=.5) views = None fragment = dom_parser2.parse_dom(html, 'span', {'class': 'post-views'}) if fragment: views = re.sub('[^\d]', '', fragment[0].content) iframe_urls = [] if video.video_type == VIDEO_TYPES.MOVIE: iframe_urls = [ r.attrs['href'] for r in dom_parser2.parse_dom( html, 'a', {'class': ['orange', 'abutton']}, req='href') ] else: for label, link in self.__get_episode_links(html): if int(label) == int(video.episode): iframe_urls.append(link) for iframe_url in iframe_urls: headers = {'Referer': url} html = self._http_get(iframe_url, headers=headers, cache_limit=.5) match = re.search('{link\s*:\s*"([^"]+)', html) if match: sources = self.__get_gk_links(match.group(1), iframe_url) else: sources = scraper_utils.parse_sources_list(self, html) for source in sources: stream_url = source + scraper_utils.append_headers( {'User-Agent': scraper_utils.get_ua()}) direct = sources[source]['direct'] quality = sources[source]['quality'] if sources[source]['direct']: host = scraper_utils.get_direct_hostname(self, source) else: host = urlparse.urlparse(source).hostname hoster = { 'multi-part': False, 'url': stream_url, 'class': self, 'quality': quality, 'host': host, 'rating': None, 'views': views, 'direct': direct } hosters.append(hoster) return hosters
def get_sources(self, video): source_url = self.get_url(video) hosters = [] if not source_url or source_url == FORCE_NO_MATCH: return hosters url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(url, cache_limit=8) hosts = [ r.content for r in dom_parser2.parse_dom( html, 'p', {'class': 'server_servername'}) ] links = [ r.content for r in dom_parser2.parse_dom(html, 'p', {'class': 'server_play'}) ] for host, link_frag in zip(hosts, links): stream_url = dom_parser2.parse_dom(link_frag, 'a', req='href') if not stream_url: continue stream_url = stream_url[0].attrs['href'] host = re.sub('^Server\s*', '', host, re.I) host = re.sub('\s*Link\s+\d+', '', host) if host.lower() == 'google': sources = self.__get_gvideo_links(stream_url) else: sources = [{'host': host, 'link': stream_url}] for source in sources: host = scraper_utils.get_direct_hostname(self, stream_url) if host == 'gvideo': quality = scraper_utils.gv_get_quality(stream_url) stream_url = source['link'] + scraper_utils.append_headers( {'User-Agent': scraper_utils.get_ua()}) direct = True else: stream_url = scraper_utils.pathify_url(source['link']) host = HOST_SUB.get(source['host'].lower(), source['host']) quality = scraper_utils.get_quality( video, host, QUALITIES.HIGH) direct = False hoster = { 'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': direct } hosters.append(hoster) return hosters
def get_sources(self, video): hosters = [] sources = {} source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=.5) for match in re.finditer( 'player-data="([^"]+)[^>]+episode-data="([^"]+)[^>]*>(.*?)</a>', html, re.DOTALL): player_url, ep_id, label = match.groups() if video.video_type == VIDEO_TYPES.EPISODE and not self.__episode_match( video, ep_id): continue label = label.strip() headers = {'Referer': page_url} if re.match('https?://embed', player_url): src_html = self._http_get(player_url, headers=headers, cache_limit=.5) sources.update(scraper_utils.parse_sources_list( self, src_html)) sources.update(self.__get_sources(src_html, label)) else: sources[player_url] = { 'direct': False, 'quality': Q_MAP.get(label.upper(), QUALITIES.HIGH) } for source, value in sources.iteritems(): direct = value['direct'] quality = value['quality'] if direct: host = scraper_utils.get_direct_hostname(self, source) stream_url = source + scraper_utils.append_headers( {'User-Agent': scraper_utils.get_ua()}) else: host = urlparse.urlparse(source).hostname stream_url = source hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': direct } hosters.append(hoster) return hosters
def __get_embedded_links(self, html, sub): hosters = [] html = html.replace('\\"', '"').replace('\\/', '/') sources = scraper_utils.parse_sources_list(self, html) for source in sources: host = scraper_utils.get_direct_hostname(self, source) quality = sources[source]['quality'] direct = sources[source]['direct'] hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': source, 'direct': direct} hoster['subs'] = sub hosters.append(hoster) return hosters
def __get_links(self, url, video): hosters = [] search_url, params = self.__translate_search(url) html = self._http_get(search_url, params=params, cache_limit=.5) js_result = scraper_utils.parse_json(html, search_url) down_url = js_result.get('downURL') dl_farm = js_result.get('dlFarm') dl_port = js_result.get('dlPort') for item in js_result.get('data', []): post_hash, size, post_title, ext, duration = item['0'], item['4'], item['10'], item['11'], item['14'] checks = [False] * 6 if not scraper_utils.release_check(video, post_title): checks[0] = True if 'alangs' in item and item['alangs'] and 'eng' not in item['alangs']: checks[1] = True if re.match('^\d+s', duration) or re.match('^[0-5]m', duration): checks[2] = True if 'passwd' in item and item['passwd']: checks[3] = True if 'virus' in item and item['virus']: checks[4] = True if 'type' in item and item['type'].upper() != 'VIDEO': checks[5] = True if any(checks): logger.log('EasyNews Post excluded: %s - |%s|' % (checks, item), log_utils.LOGDEBUG) continue stream_url = down_url + urllib.quote('/%s/%s/%s%s/%s%s' % (dl_farm, dl_port, post_hash, ext, post_title, ext)) stream_url = stream_url + '|Authorization=%s' % (urllib.quote(self.auth)) host = scraper_utils.get_direct_hostname(self, stream_url) quality = None if 'width' in item: try: width = int(item['width']) except: width = 0 if width: quality = scraper_utils.width_get_quality(width) if quality is None: if video.video_type == VIDEO_TYPES.MOVIE: meta = scraper_utils.parse_movie_link(post_title) else: meta = scraper_utils.parse_episode_link(post_title) quality = scraper_utils.height_get_quality(meta['height']) if self.max_bytes: match = re.search('([\d.]+)\s+(.*)', size) if match: size_bytes = scraper_utils.to_bytes(*match.groups()) if size_bytes > self.max_bytes: logger.log('Result skipped, Too big: |%s| - %s (%s) > %s (%s GB)' % (post_title, size_bytes, size, self.max_bytes, self.max_gb)) continue hoster = {'multi-part': False, 'class': self, 'views': None, 'url': stream_url, 'rating': None, 'host': host, 'quality': quality, 'direct': True} if any(i for i in ['X265', 'HEVC'] if i in post_title.upper()): hoster['format'] = 'x265' if size: hoster['size'] = size if post_title: hoster['extra'] = post_title hosters.append(hoster) return hosters
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=8) fragment = dom_parser2.parse_dom(html, 'div', {'class': 'playex'}) if fragment: html = fragment[0].content iframe_url = dom_parser2.parse_dom(html, 'iframe', req='src') if not iframe_url: return hosters iframe_url = iframe_url[0].attrs['src'] if iframe_url.startswith('/'): iframe_url = scraper_utils.urljoin(self.base_url, iframe_url) html = self._http_get(iframe_url, headers={'Referer': page_url}, cache_limit=.5) obj = dom_parser2.parse_dom(html, 'object', req='data') if obj: streams = dict((stream_url, { 'quality': scraper_utils.gv_get_quality(stream_url), 'direct': True }) for stream_url in scraper_utils.parse_google( self, obj[0].attrs['data'])) else: streams = scraper_utils.parse_sources_list(self, html) for stream_url, values in streams.iteritems(): host = scraper_utils.get_direct_hostname(self, stream_url) if host == 'gvideo': quality = scraper_utils.gv_get_quality(stream_url) else: quality = values['quality'] stream_url += scraper_utils.append_headers({ 'User-Agent': scraper_utils.get_ua(), 'Referer': page_url }) source = { 'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': True } hosters.append(source) return hosters
def __get_gk_links(self, link, iframe_url): sources = {} data = {'link': link} headers = XHR headers.update({'Referer': iframe_url, 'User-Agent': USER_AGENT}) html = self._http_get(GK_URL, data=data, headers=headers, cache_limit=.25) js_data = scraper_utils.parse_json(html, GK_URL) if 'link' in js_data: if isinstance(js_data['link'], basestring): stream_url = js_data['link'] if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo': for source in scraper_utils.parse_google(self, stream_url): sources[source] = { 'quality': scraper_utils.gv_get_quality(source), 'direct': True } else: sources[stream_url] = { 'quality': QUALITIES.HIGH, 'direct': False } else: for link in js_data['link']: stream_url = link['link'] if scraper_utils.get_direct_hostname( self, stream_url) == 'gvideo': quality = scraper_utils.gv_get_quality(stream_url) elif 'label' in link: quality = scraper_utils.height_get_quality( link['label']) else: quality = QUALITIES.HIGH sources[stream_url] = {'quality': quality, 'direct': True} return sources
def __get_gk_links2(self, html): sources = {} match = re.search('proxy\.link=([^"&]+)', html) if match: proxy_link = match.group(1) proxy_link = proxy_link.split('*', 1)[-1] if len(proxy_link) <= 224: vid_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY1, proxy_link) else: vid_url = scraper_utils.gk_decrypt(self.get_name(), GK_KEY2, proxy_link) if scraper_utils.get_direct_hostname(self, vid_url) == 'openload.co': for source in self._parse_gdocs(vid_url): sources[source] = {'quality': scraper_utils.gv_get_quality(source), 'direct': True} return sources
def __get_sources(self, html): sources = scraper_utils.parse_sources_list(self, html) for source in dom_parser2.parse_dom( html, 'source', {'type': 'video/mp4'}, req='src') + dom_parser2.parse_dom(html, 'iframe', req='src'): source = source.attrs['src'] if scraper_utils.get_direct_hostname(self, source) == 'gvideo': quality = scraper_utils.gv_get_quality(source) direct = True else: quality = QUALITIES.HD720 direct = False sources[source] = {'quality': quality, 'direct': direct} return self.__proc_sources(sources)
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=.5) iframe_url = dom_parser2.parse_dom(html, 'iframe', {'id': 'myiframe'}, req='src', exclude_comments=True) if not iframe_url: return hosters iframe_url = iframe_url[0].attrs['src'] html = self._http_get(iframe_url, headers={'Referer': page_url}, cache_limit=.5) for source in dom_parser2.parse_dom(html, 'source', {'type': 'video/mp4'}, req=['src', 'data-res']): stream_url = source.attrs['src'] host = scraper_utils.get_direct_hostname(self, stream_url) if host == 'gvideo': quality = scraper_utils.gv_get_quality(stream_url) stream_url += scraper_utils.append_headers( {'User-Agent': scraper_utils.get_ua()}) else: quality = scraper_utils.height_get_quality( source.attrs['data-res']) stream_url += scraper_utils.append_headers({ 'User-Agent': scraper_utils.get_ua(), 'Referer': page_url }) source = { 'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': True } hosters.append(source) return hosters
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters page_url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(page_url, cache_limit=0) match = re.search('var\s*video_id\s*=\s*"([^"]+)', html) if not match: return hosters video_id = match.group(1) headers = {'Referer': page_url} headers.update(XHR) _html = self._http_get(scraper_utils.urljoin(self.base_url, 'av'), headers=headers, method='POST', cache_limit=0) vid_url = scraper_utils.urljoin(self.base_url, VIDEO_URL) html = self._http_get(vid_url, data={'v': video_id}, headers=headers, cache_limit=0) for source, value in scraper_utils.parse_json(html, vid_url).iteritems(): match = re.search('url=(.*)', value) if not match: continue stream_url = urllib.unquote(match.group(1)) host = scraper_utils.get_direct_hostname(self, stream_url) if host == 'gvideo': quality = scraper_utils.gv_get_quality(stream_url) else: quality = scraper_utils.height_get_quality(source) stream_url += scraper_utils.append_headers( {'User-Agent': scraper_utils.get_ua()}) hoster = { 'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True } hosters.append(hoster) return hosters
def get_sources(self, video): hosters = [] source_url = self.get_url(video) if not source_url or source_url == FORCE_NO_MATCH: return hosters url = scraper_utils.urljoin(self.base_url, source_url) html = self._http_get(url, cache_limit=8) for _attrs, fragment in dom_parser2.parse_dom(html, 'div', {'class': 'movieplay'}): iframe_src = dom_parser2.parse_dom(fragment, 'iframe', req='src') if iframe_src: iframe_src = iframe_src[0].attrs['src'] if re.search('o(pen)?load', iframe_src, re.I): meta = scraper_utils.parse_movie_link(iframe_src) quality = scraper_utils.height_get_quality(meta['height']) links = {iframe_src: {'quality': quality, 'direct': False}} else: links = self.__get_links(iframe_src, url) for link in links: direct = links[link]['direct'] quality = links[link]['quality'] if direct: host = scraper_utils.get_direct_hostname(self, link) if host == 'gvideo': quality = scraper_utils.gv_get_quality(link) stream_url = link + scraper_utils.append_headers( { 'User-Agent': scraper_utils.get_ua(), 'Referer': url }) else: host = urlparse.urlparse(link).hostname stream_url = link source = { 'multi-part': False, 'url': stream_url, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'direct': direct } hosters.append(source) return hosters